Reasoning Capability
Reasoning capability in large language models (LLMs) is a central research area focusing on enhancing their ability to solve complex problems requiring multiple steps and logical inferences. Current research investigates various prompting techniques, such as chain-of-thought prompting and retrieval-augmented generation (RAG), to improve reasoning performance across diverse tasks, including mathematical, logical, and commonsense reasoning, often using benchmarks like GSM8K and its variants. These efforts aim to understand the limitations of current LLMs, which often rely on pattern matching rather than true logical deduction, and to develop more robust and reliable reasoning methods. The ultimate goal is to create LLMs capable of genuine reasoning, impacting fields ranging from scientific discovery to personalized education and decision support systems.
Papers - Page 2
SWI: Speaking with Intent in Large Language Models
Yuwei Yin, EunJeong Hwang, Giuseppe CareniniUniversity of British Columbia●Vector Institute for AIR-PRM: Reasoning-Driven Process Reward Modeling
Shuaijie She, Junxiao Liu, Yifeng Liu, Jiajun Chen, Xin Huang, Shujian HuangNanjing University●China Mobile Communications Company Limited Research Institute
The Art of Tool Interface Design
Yunnan Wu, Paul Chen, Deshank Baranwal, Jinlong Zhou, Jian YuanMeta Inc.Understanding R1-Zero-Like Training: A Critical Perspective
Zichen Liu, Changyu Chen, Wenjun Li, Penghui Qi, Tianyu Pang, Chao Du, Wee Sun Lee, Min LinSea AI Lab●National University of Singapore●Singapore Management UniversityReasoning Beyond Limits: Advances and Open Problems for LLMs
Mohamed Amine Ferrag, Norbert Tihanyi, Merouane Debbah
Innate Reasoning is Not Enough: In-Context Learning Enhances Reasoning Large Language Models with Less Overthinking
Yuyao Ge, Shenghua Liu, Yiwei Wang, Lingrui Mei, Lizhe Chen, Baolong Bi, Xueqi ChengAI Safety of Chinese Academy of Sciences●University of Chinese Academy of Sciences●University of California●Tsinghua UniversityImageGen-CoT: Enhancing Text-to-Image In-context Learning with Chain-of-Thought Reasoning
Jiaqi Liao, Zhengyuan Yang, Linjie Li, Dianqi Li, Kevin Lin, Yu Cheng, Lijuan WangMicrosoft●The Chinese University of Hong Kong
OpenVLThinker: An Early Exploration to Complex Vision-Language Reasoning via Iterative Self-Improvement
Yihe Deng, Hritik Bansal, Fan Yin, Nanyun Peng, Wei Wang, Kai-Wei ChangLos AngelesDoes Chain-of-Thought Reasoning Help Mobile GUI Agent? An Empirical Study
Li Zhang, Longxi Gao, Mengwei XuBeijing University of Posts and Telecommunications
Reinforcement Learning for Reasoning in Small LLMs: What Works and What Doesn't
Quy-Anh Dang, Chris NgoVNU University of Science●Knovel Engineering LabMathFusion: Enhancing Mathematic Problem-solving of LLM through Instruction Fusion
Qizhi Pei, Lijun Wu, Zhuoshi Pan, Yu Li, Honglin Lin, Chenlin Ming, Xin Gao, Conghui He, Rui YanRenmin University of China●Shanghai AI Laboratory●Tsinghua University●Shanghai Jiao Tong University●Wuhan UniversityDNA Bench: When Silence is Smarter -- Benchmarking Over-Reasoning in Reasoning LLMs
Masoud Hashemi, Oluwanifemi Bamgbose, Sathwik Tejaswi Madhusudhan, Jishnu Sethumadhavan Nair, Aman Tiwari, Vikas YadavServiceNow
Unlocking General Long Chain-of-Thought Reasoning Capabilities of Large Language Models via Representation Engineering
Xinyu Tang, Xiaolei Wang, Zhihao Lv, Yingqian Min, Wayne Xin Zhao, Binbin Hu, Ziqi Liu, Zhiqiang ZhangRenmin University of China●Ant GroupReinforcement Learning Outperforms Supervised Fine-Tuning: A Case Study on Audio Question Answering
Gang Li, Jizhong Liu, Heinrich Dinkel, Yadong Niu, Junbo Zhang, Jian LuanXiaomi CorporationLarge Reasoning Models in Agent Scenarios: Exploring the Necessity of Reasoning Capabilities
Xueyang Zhou, Guiyao Tie, Guowen Zhang, Weidong Wang, Zhigang Zuo, Di Wu, Duanfeng Chu, Pan Zhou, Lichao Sun, Neil Zhenqiang GongHuazhong University of Science and Technology●Universiti Malaya●Wuhan University of Technology●Lehigh University●Duke University